Stack Overflow
Stack Overflow

Questions tagged [multivariate-time-series]

96 questions
0
votes
0 answers

LSTM does not predict outputs having been trained with one-hot-encoded dataframe

I try to apply a multivariate forecasting on a df like this: initial dataframe I transformed the dataset to one-hot-encoding to feed it to an LSTM one_hot_encoder = OneHotEncoder(handle_unknown='ignore') results =…
irene noLaz
  • 1
  • 1
0
votes
0 answers

NaN values in loss and weights while training LSTM with Keras

I am trying to code an LSTM that takes as input 7 daily channel spendings and tries to predict the daily sales. After the first epoch loss value is nan and weights are all nan. And it stays like that. I tried different learning rates and…
Yağız Dereboy
  • 1
0
votes
0 answers

How can I format my time series data for PyTorch LSTM classification?

How can I pre-process time series data for a classification problem and feed it into the PyTorch LSTM model? I have the dataset like the below picture. How can I pre-process the dataset to feed it to the LSTM model? Here, event_type is the target…
Nosin Ibna Mahbub
  • 1
0
votes
0 answers

Best method to impute time series with missing values in early years when time series will be differenced

I am building a VARMAX model with endogenous and exogenous time series variables. The dataset consists of years 1950-2019 for all time series variables except one exogenous variable which was not available until 1982. The time series are not…
KateBon
  • 31
  • 1
0
votes
1 answer

how Darts Time Series forecasting library deals with covariates under the surface? why is the prediction not changing with the change of covariates?

I am trying to understand why the model's prediction is independent of the changes of covariates. Given any random target series : y_train_trans and past_Covariate series : X_train_trans , i am finding that pred1 and pred 2 always end up exactly the…
Sandy Al Akhras
  • 139
  • 3
  • 10
0
votes
0 answers

problem in R when trying to access the results of my serial tests for a VAR model

I have estimated several VAR models, which I would now like to compare looking at the residuals. I have tried several ways to access the residuals but none seem to work. Maybe it is because R does not seem to understand when I indedx $pval, as the…
gerardlambert
  • 47
  • 7
0
votes
0 answers

seasonal decomposition of a time series in R - problem determining if multiplicative or additive is best on R

I am currently working on a bivariate time series that I would like to model using a VAR model. I am trying to assess using an STL decomposition if the seasonal trend is significant and should be integrated in my VAR model (if other tests, like…
gerardlambert
  • 47
  • 7
0
votes
1 answer

How to use statsmodels' DynamicFactor method with exogenous variables?

I have a multivariate dynamic factor model with one common factor that I want to estimate with statsmodels.tsa.statespace.dynamic_factor.DynamicFactor. The model looks as follows: Model formulation in LaTeX.* As you can see, I am dealing with a t x…
user21551428
  • 3
  • 3
0
votes
0 answers

Avoiding overfitting in panel data and explainable ai

I have panel data consisting of yearly credit ratings as a target variable and some features for its estimation. Each year of my 20 year time series i have around 400 firms. I use shap to analyse some of those features and analyse how this results…
Soph
  • 1
0
votes
1 answer

PyCaret v3.0 - _CURRENT_EXPERIMENT global variable is not set

We are getting the following error after running either check_stats() or compare_models() functions from PyCaret versiob 3.0.x; "_CURRENT_EXPERIMENT global variable is not set. Please run setup() first." Is there any pointer that how this can be…
user3634141
  • 15
  • 3
0
votes
2 answers

Convert a time series dataset with multiple date columns into a time series with a unique date column or into a zoo object

I have a large dataset made of multiple irregular timeseries with a specific date column for each series. I want to convert this dataset into a dataframe with a unique date column or into a zoo object. I tried read_xls(), read.zoo(). I tried to…
Bertrand G
  • 37
  • 6
0
votes
0 answers

Multivariate time series RNN (LSTM) issues for player stat predictions

I am working on a custom project where I am trying to predict baseball batting and pitching stats for all players within my dataset from 1970 - 2022. For simplicity and to reduce potential clutter I am only going to refer to my batting dataset.…
DJB17
  • 21
  • 5
0
votes
0 answers

When performing model selection with ForecastingGridSearchCV in sktime, why do you need to specify a forecaster to instantiate the gridsearch?

In the Pydata 2022 Global sktime tutorial on AutoML there is an example of using sktime.forecasting.model_selection.ForecastingGridSearchCV to select a forecaster: from sktime.forecasting.theta import ThetaForecaster from sktime.forecasting.trend…
teejk
  • 25
  • 4
0
votes
0 answers

Time series : add constants for each time series

I have N time series of shape (30*36) (time step, feature). For each time series 500 parameters that can be seen as the history of the time series have to be added. This parameters are different for each time series. For now, the way I found to feed…
Ketchup
  • 150
  • 11
0
votes
1 answer

Does Multivariate LSTM model input different type of input?

I am a newbie to deep learning and am trying to build a LSTM model capable of predicting users' points. Points are given to users based on their lifestyle and others parameters. My dataset df contains two columns, one for user ID and the second for…
coumbs
  • 3
  • 2
1 2
3
4 5 6 7